Virtual Segment Rebuild Based on Power-Aware Data Portions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing database systems face limitations in processing speed due to hardware constraints, data storage methods, and restricted co-processing options, leading to inefficiencies in query execution.
Innovation Solution
A database system architecture that employs parallelized data input, storage, retrieval, and query processing systems, utilizing segmenting and restructuring techniques to optimize data storage and processing, allowing concurrent execution of queries across distributed computing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If data is stored in traditional sequential manner, then storage simplicity is maintained, but query execution speed deteriorates
Solution Approach 1:
The patent divides data into virtual segments that can be independently processed and stored across distributed computing resources. Each virtual segment represents a portion of the data that can be accessed and processed separately, enabling parallel query execution across multiple computing devices while maintaining organized data structure through segment identifiers and metadata.
2Productivity
If parallel processing is implemented, then query processing speed is improved, but system complexity increases
Solution Approach 1:
The patent creates a universal virtual segment structure that can be used across different computing devices and query types. The virtual segment format, metadata structure, and recovery mechanisms are designed to be general-purpose, allowing the same architecture to handle various query operations (SELECT, INSERT, UPDATE, DELETE) across distributed resources without requiring device-specific implementations.
Solution Approach 2:
The patent introduces virtual segments as intermediary data structures between the physical storage system and query processing operations. These virtual segments act as mediators that abstract the complexity of distributed storage management, allowing queries to be processed in parallel while the system automatically handles segment recovery, redistribution, and coordination through ownership sequence numbers and recovery logs.
3Power
If data is redistributed across computing devices, then processing capacity is increased, but data access complexity increases
Solution Approach 1:
The patent implements feedback mechanisms through ownership sequence numbers that track data segment ownership and location across computing devices. When queries are executed, the system uses these sequence numbers to automatically determine which computing device holds the required virtual segments, enabling efficient data access without complex manual routing. The feedback loop continuously updates ownership information to reflect data redistribution.
Data Source
AI summary
A database system operates by: identifying at least two data portions in a first segment for rebuilding, wherein the at least two data portions is a proper subset of a plurality of sequential data portions; generating a locally rebuilt set of rows for the at least two data portions based on power consumption and: determining at least two corresponding data portions of at least one other segment in the segment group required to rebuild the at least two data portions; retrieving the at least two corresponding data portions of the at least one other segment from storage; and utilizing the retrieved at least two corresponding data portions to rebuild the at least two data portions based on the redundancy coding scheme.